> For the complete documentation index, see [llms.txt](https://docs.mediarithmics.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mediarithmics.io/audience-and-activation/target-contextually/contextual-reference/panel-based-targeting.md).
# Panel-based targeting
Derive the content to target from the content a seed audience consumes, using lift and reach.
## What it is
Panel-based targeting builds a list of URLs by analysing the content consumed by a specific seed audience - the **panel**. You supply the people; the platform finds the content they over-consume.
## How the analysis works
{% stepper %}
{% step %}
### Your audience segment is analysed
The platform determines which URLs are over-represented in the segment compared with your overall audience.
{% endstep %}
{% step %}
### Those URLs are analysed semantically
The relevant keywords are extracted and one or more IAB categories are associated, so that recently published URLs - which do not yet have enough page views of their own - can be categorised automatically.
{% endstep %}
{% step %}
### Matching pages carry the segment IDs
When a user visits a URL linked to one or more audience segments, the IDs of those segments are transmitted to your activation platforms through key-value targeting, so personalised advertising can be displayed.
{% endstep %}
{% endstepper %}
## Lift and reach
These two figures are what you actually configure, and they pull against each other.
| Figure | What it measures |
| --------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| **Lift** | How over-represented a piece of content is in the panel compared with the whole datamart. |
| **Reach** | How much a particular piece of content has been seen during the last 30 days by users in this segment, compared with the whole datamart. |
You select a **lift threshold**, and the interface shows the expected reach based on the past 30 days. That pair determines the **targeted page views ratio**, and it is the ratio - not the raw threshold - that is used to recalculate the appropriate lift threshold for URL selection every night.
{% hint style="info" %}
Raising the lift threshold selects content that is more distinctive of your panel and less of it, so reach falls. Lowering it broadens the content set and dilutes how characteristic it is. The interface lets you work out dynamically which URLs a given lift value will target before you activate.
{% endhint %}
## What happens once it is live
Once settings are activated, semantic analysis is run on the targeted content picked by your lift configuration. That is what lets the platform categorise URLs it has not seen before, and it gives you insight into what kind of content the users in this segment mostly browse.
Three things are recalculated **every night**:
* The **lift** of each URL, and therefore the targeted content of every segment where contextual targeting is activated.
* The **semantic analysis**.
* The **contextual targeting JavaScript tag**, so it accounts for new segments where contextual targeting has been activated, and new URLs compared against a segment's semantic extraction.
{% hint style="info" %}
Only URLs with a minimum number of page views are taken into account. Consult your Account manager to check or update the minimum for your organisation.
{% endhint %}
You can still edit your settings after activation, with **Edit these settings**.
## Its targeting key
A panel-based list activates under the targeting key `ct_panel_mics`, carrying the **segment ID** as the targeting value. See [Contextual activation](/audience-and-activation/target-contextually/contextual-reference/contextual-activation.md#the-targeting-keys).
## Related pages
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.mediarithmics.io/audience-and-activation/target-contextually/contextual-reference/panel-based-targeting.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.